https://github.com/sagarbhavsar1/single-image-dehazing-using-feature-extraction-techniques-in-deep-learning
This is a novel methodology to perform dehazing process on a single outdoor Image using feature extraction techniques in Deep Learning and 3 added pre-processing steps.
https://github.com/sagarbhavsar1/single-image-dehazing-using-feature-extraction-techniques-in-deep-learning
artificial-intelligence cnn dehazing image-processing machine-learning python science technology vgg16-model
Last synced: 6 months ago
JSON representation
This is a novel methodology to perform dehazing process on a single outdoor Image using feature extraction techniques in Deep Learning and 3 added pre-processing steps.
- Host: GitHub
- URL: https://github.com/sagarbhavsar1/single-image-dehazing-using-feature-extraction-techniques-in-deep-learning
- Owner: sagarbhavsar1
- Created: 2022-12-16T20:07:34.000Z (almost 3 years ago)
- Default Branch: main
- Last Pushed: 2024-07-29T18:44:28.000Z (about 1 year ago)
- Last Synced: 2024-07-30T00:55:49.635Z (about 1 year ago)
- Topics: artificial-intelligence, cnn, dehazing, image-processing, machine-learning, python, science, technology, vgg16-model
- Language: Jupyter Notebook
- Homepage:
- Size: 71.8 MB
- Stars: 2
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Single-Image-Dehazing-using-feature-extraction-techniques-in-Deep-Learning
This is a novel methodology to perform dehazing process on a single outdoor Image using feature extraction techniques in Deep Learning and 3 added pre-processing steps.
Dataset used for training and validation is SOTS outdoor [available here](https://www.kaggle.com/wwwwwee/dehaze).
Detailed explanation and documentation available [here](https://github.com/sagarbhavsar1/Single-Image-Dehazing-using-feature-extraction-techniques-in-Deep-Learning/blob/main/Final%20Report_Image_dehazing%20(3).pdf )
Follow the following steps to run the code:
1. Download the image datasets from kaggle- link :- https://www.kaggle.com/datasets/wwwwwee/dehaze
2. Create separate folders for each specific dataset type: hazy images, clear images and hazy test images.
2. Open the VGG16 CNN model on Google colab/Google colab pro
3. Run the code (provide proper dataset path for input to the model)
4. Please note that you may have to run the VGG16 model network function code-block again once the model is trained (for executing pruning without error).
5. Provide the path for hazy test images to the trained model and run the block of code.
6. Dehazed image will be generated by the model.